Out-Of-Vocabulary (OOV) Word Detection System

An Out-Of-Vocabulary (OOV) Word Detection System is a word detection system that can detect OOV words.

• AKA: OOV Word Recognizer.
• Context:
  • It can solve a OOV Word Detection Task by implementing OOV Word Detection Algorithm.
  • It can rely on a OOV Word Modeling System and a OOV Word Embedding System.
  • It can be evaluated by a OOV Word Detection Benchmark Task (that measures an OOV word error rate).
  • It can be part of a OOV Word Machine Translation System.
  • ...
• Example(s):
  • Maximum Entropy OOV Detection System,
  • Filler Model and Confusion Network Based OOV Detection System (e.g. Rastrow et al., 2009).
  • …
• Counter-Example(s):
  • IV Word Detection System,
  • Character Detection System,
  • Subword Detection System,
  • Phrase Detection System.
• See: Word Embedding System, Text Generation System, Automatic Text Translation System, Natural Language Processing System.

---

---

References

2010

• (Parada et al., 2010) ⇒ Carolina Parada, Mark Dredze, Denis Filimonov, and Frederick Jelinek. (2010). “Contextual Information Improves OOV Detection in Speech.” In: Proceedings of the Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics (HLT-NAACL 2010).

2009

• (Rastrow, 2009a) ⇒ Ariya Rastrow, Abhinav Sethy, and Bhuvana Ramabhadran (2009). “A New Method for OOV Detection Using Hybrid Word/Fragment System". In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009).

---

---